New! View global litigation for patent families

US6430551B1 - Vocabulary and/or language model training - Google Patents

Vocabulary and/or language model training Download PDF

Info

Publication number
US6430551B1
US6430551B1 US09167424 US16742498A US6430551B1 US 6430551 B1 US6430551 B1 US 6430551B1 US 09167424 US09167424 US 09167424 US 16742498 A US16742498 A US 16742498A US 6430551 B1 US6430551 B1 US 6430551B1
Authority
US
Grant status
Grant
Patent type
Prior art keywords
system
model
recognition
documents
search
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
US09167424
Inventor
Eric Thelen
Stefan Besling
Steven DeJarnett
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Koninklijke Philips NV
Original Assignee
Koninklijke Philips NV
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Grant date

Links

Images

Classifications

    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09BEDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B19/00Teaching not covered by other main groups of this subclass
    • G09B19/06Foreign languages
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99934Query formulation, input preparation, or translation
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10TECHNICAL SUBJECTS COVERED BY FORMER USPC
    • Y10STECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y10S707/00Data processing: database and file management or data structures
    • Y10S707/99931Database or file accessing
    • Y10S707/99933Query processing, i.e. searching
    • Y10S707/99936Pattern matching access

Abstract

A system includes means for creating a vocabulary and/or statistical language model from a textual training corpus. The vocabulary and/or language model are used in a pattern recognition system, such as a speech recognition system or a handwriting recognition system, for recognizing a time-sequential input pattern. The system includes means for determining at least one context identifier and means for deriving at least one search criterion, such as a keyword, from the context identifier. The system further includes means for selecting documents from a set of documents based on the search criterion. Advantageously, an Internet search engine is used for selecting the documents. Means are used for composing the training corpus from the selected documents.

Description

BACKGROUND OF THE INVENTION

The invention relates to a method for creating a vocabulary and/or statistical language model from a textual training corpus for subsequent use by a pattern recognition system.

The invention further relates to a system for creating a vocabulary and/or a statistical language model for subsequent use by a pattern recognition system; the system comprising means for creating the vocabulary and/or statistical language model from a textual training corpus.

The invention also relates to a pattern recognition system for recognising a time-sequential input pattern using a vocabulary and/or statistical language model; the pattern recognition system comprising the system for creating a vocabulary and/or statistical language model from a textual training corpus.

Pattern recognition systems, such as large vocabulary continuous speech recognition systems or handwriting recognition systems, typically use a vocabulary to recognise words and a language model to improve the basic recognition result. FIG. 1 illustrates a typical large vocabulary continuous speech recognition system 100 [refer L. Rabiner, B-H. Juang, “Fundamentals of speech recognition”, Prentice Hall 1993, pages 434 to 454]. The system 100 comprises a spectral analysis subsystem 110 and a unit matching subsystem 120. In the spectral analysis subsystem 110 the speech input signal (SIS) is spectrally and/or temporally analysed to calculate a representative vector of features (observation vector, OV). Typically, the speech signal is digitised (e.g. sampled at a rate of 6.67 kHz.) and pre-processed, for instance by applying pre-emphasis. Consecutive samples are grouped (blocked) into frames, corresponding to, for instance, 32 msec. of speech signal. Successive frames partially overlap, for instance, 16 msec. Often the Linear Predictive Coding (LPC) spectral analysis method is used to calculate for each frame a representative vector of features (observation vector). The feature vector may, for instance, have 24, 32 or 63 components. In the unit matching subsystem 120, the observation vectors are matched against an inventory of speech recognition units. A speech recognition unit is represented by a sequence of acoustic references. Various forms of speech recognition units may be used. As an example, a whole word or even a group of words may be represented by one speech recognition unit. A word model (WM) provides for each word of a given vocabulary a transcription in a sequence of acoustic references. For systems, wherein a whole word is represented by a speech recognition unit, a direct relationship exists between the word model and the speech recognition unit. Other systems, in particular large vocabulary systems, may use for the speech recognition unit linguistically based sub-word units, such as phones, diphones or syllables, as well as derivative units, such as fenenes and fenones. For such systems, a word model is given by a lexicon 134, describing the sequence of sub-word units relating to a word of the vocabulary, and the sub-word models 132, describing sequences of acoustic references of the involved speech recognition unit. A word model composer 136 composes the word model based on the subword model 132 and the lexicon 134. FIG. 2A illustrates a word model 200 for a system based on whole-word speech recognition units, where the speech recognition unit of the shown word is modelled using a sequence of ten acoustic references (201 to 210). FIG. 2B illustrates a word model 220 for a system based on sub-word units, where the shown word is modelled by a sequence of three sub-word models (250, 260 and 270), each with a sequence of four acoustic references (251, 252, 253, 254; 261 to 264; 271 to 274). The word models shown in FIG. 2 are based on Hidden Markov Models, which are widely used to stochastically model speech and handwriting signals. Using this model, each recognition unit (word model or subword model) is typically characterised by an HMM, whose parameters are estimated from a training set of data. For large vocabulary speech recognition systems involving, for instance, 10,000 to 60,000 words, usually a limited set of, for instance 40, sub-word units is used, since it would require a lot of training data to adequately train an HMM for larger units. A HMM state corresponds to an acoustic reference (for speech recognition) or an allographic reference (for handwriting recognition). Various techniques are known for modelling a reference, including discrete or continuous probability densities.

A word level matching system 130 matches the observation vectors against all sequences of speech recognition units and provides the likelihoods of a match between the vector and a sequence. If sub-word units are used, constraints are placed on the matching by using the lexicon 134 to limit the possible sequence of sub-word units to sequences in the lexicon 134. This reduces the outcome to possible sequences of words. A sentence level matching system 140 uses a language model (LM) to place further constraints on the matching so that the paths investigated are those corresponding to word sequences which are proper sequences as specified by the language model. In this way, the outcome of the unit matching subsystem 120 is a recognised sentence (RS). The language model used in pattern recognition may include syntactical and/or semantical constraints 142 of the language and the recognition task. A language model based on syntactical constraints is usually referred to as a grammar 144.

Similar systems are known for recognising handwriting. The language model used for a handwriting recognition system may in addition to or as an alternative to specifying word sequences specify character sequences.

The grammar 144 used by the language model provides the probability of a word sequence W=w1w2w3 . . . wq, which in principle is given by:

P(W)=P(w 1)P(w 2 |w 1). P(w 3 |w 1 w 2) . . . P(w q |w 1 w 2 w 3 . . . w q).

Since in practice it is infeasible to reliably estimate the conditional word probabilities for all words and all sequence lengths in a given language, N-gram word models are widely used. In an N-gram model, the term P(wj|w1w2w3 . . . wj−1) is approximated by P(wj|wj−N+1 . . . wj−1). In practice, bigrams or trigrams are used. In a trigram, the term P(wj|w1w2w3 . . . Wj−1) is approximated by P(wj|wj−2wj−1).

The invention relates to recognition systems which use a vocabulary and/or a language model which can, preferably automatically, be build from a textual training corpus. A vocabulary can be simply retrieved from a document by collecting all different words in the document. The set of words may be reduced, for instance, to words which occur frequently in the document (in absolute terms or relative terms, like relative to other words in the document, or relative with respect to a frequency of occurrence in default documents).

A way of automatically building an N-gram language model is to estimate the conditional probabilities P(wj|wj−N+1 . . . wj−1) by a simple relative frequency: F(wj−N+1 . . . wj−1wj)/F(wj−N+1 . . . Wj−1), in which F is the number of occurrences of the string in its argument in the given textual training corpus. For the estimate to be reliable, F(wj−N+1 . . . wj−1wj) has to be substantial in the given corpus. One way of achieving this is to use an extremely large training corpus, which covers most relevant word sequences. This is not a practical solution for most systems, since the language model becomes very large (resulting in a slow or degraded recognition and high storage requirements). Another approach is to ensure that the training corpus is representative of many words and word sequences used for a specific recognition task. This can be achieved by manually collecting documents relevant for a specific category of user, such as a radiologist, a surgeon or a legal practitioner. However, such an approach is not possible for recognition systems targeted towards users whose specific interests are not known in advance. Moreover, if a user develops a new interest, a default provided vocabulary and language model will not reflect this, resulting in a degraded recognition result.

SUMMARY OF THE INVENTION

It is an object of the invention to create a vocabulary and/or language model which is better tailored to specific user interests. A further object is to create a vocabulary and/or language model which allows improved or faster recognition.

To achieve the object, the method comprises the steps of determining at least one context identifier; deriving at least one search criterion from the context identifier; selecting documents from a set of documents based on the search criterion; and composing the training corpus from the selected documents. By searching for documents based on a search criterion derived from a context identifier, pertinent documents are collected in an effective way, ensuring that pertinent language elements are covered. This increases the quality of recognition. Moreover, also many irrelevant language elements will not be included, allowing the creation of a relatively small vocabulary or language model. This in turn can lead to a faster recognition or, alternatively, improve the recognition rate by adding more elements, such as acoustic data or allographic data, in other parts of the recognition system.

In an embodiment according to the invention, the context identifier comprises a keyword, which acts as the search criterion. For instance, the (prospective) user of a pattern recognition system specifies one or more keywords, based on which the documents are selected.

In another embodiment according to the invention, the context identifier indicates a sequence of words, such as a phrase or a text. From this sequence of words, one or more keywords are extracted, which act as the search criterion. For instance, the (prospective) user of a pattern recognition system specifies one or more documents representative of his interests. Keywords are extracted from the documents, and additional documents are selected based on the keywords. In this way, the user is relieved from choosing keywords.

In another embodiment according to the invention, the set of documents is formed by a document database or document file system. As an example, a large volume storage system, such as a CD-ROM or DVD, containing a large and diverse set of documents may be supplied with the pattern recognition system, allowing the (prospective) user to select pertinent documents from this set.

In another embodiment according to the invention, the set of documents is formed by documents in a distributed computer system. This allows for centrally storing (e.g. in a server) a larger set of documents than would normally be feasible to store or provide to a client computer on which the pattern recognition system is to be executed. Alternatively, a very large set of documents may be distributed over several servers. A good example of this last situation is Internet. Particularly if a system like Internet is used, many of the selected documents will reflect the language used at that moment, allowing for an upto-date vocabulary and/or language model to be created.

In another embodiment according to the invention, a network search engine, like those commonly used on Internet, is used to identify relevant documents based on the search criteria supplied to the search engine.

In another embodiment according to the invention, a network search agent, which autonomously searches the distributed computer system based on the search criterion, is used to identify relevant documents and, optionally, for retrieving the documents.

In another embodiment according to the invention, the training corpus is updated at a later moment selecting at least one further document from the set of documents and combining the further document with at least one previously selected document to form the training corpus. Particularly, if such updating is based on recent documents (e.g. retrieved via Internet), the language model can be kept up-to-date.

To achieve the object, the pattern recognition system is characterised in that the system comprises: means for determining at least one context identifier; means for deriving at least one search criterion from the context identifier; means for selecting documents from a set of documents based on the search criterion; and means for composing the training corpus from the selected documents. These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments shown in the drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates a speech recognition system,

FIG. 2 shows Hidden Markov Models for modelling word or sub-word units,

FIG. 3 illustrates a block diagram of the system according to the invention,

FIG. 4 shows a further embodiment of the system, and

FIG. 5 shows the system operating in a distributed computer system.

DESCRIPTION OF THE PREFERED EMBODIMENT

FIG. 3 illustrates a block diagram of a system 300 according to the invention. The system comprising means 310 for creating a vocabulary and/or statistical language model from a textual training corpus. The created vocabulary and/or language model is stored using storing means 320. The system will normally be implemented on a computer, such as a PC or a workstation, and operated under control of a suitable program loaded in the processor of the computer. The output of the system (the vocabulary and/or the language model) is supplied to a pattern recognition system, for instance like the one illustrate in FIG. 1. To this end, the information in the storing means 320 may be loaded onto any removable storage medium, such as a CD-ROM, or DVD and reloaded into the pattern recognition system. It will be appreciated that the transfer may also occur via other means, such as a computer network. In such embodiments, the system according to the invention is physically separate from the pattern recognition system. Such an approach may advantageously be used where the system according to the invention is operational at the site of a retailer, which creates the vocabulary and/or language model according to the wishes of a customer system and stores the output into the pattern recognition system acquired by the user. Preferably, the system 300 is combined with the pattern recognition system 350 as shown in FIG. 3, where the vocabulary and/or the language model form the interface 330 between both sub-systems 300 and 350. The pattern recognition system (100, 350) is capable of recognising patterns representing language representative signals created by a person. An example of such signals are speech signals or handwriting signals. In principle, the pattern is a time-sequential pattern, although it will be appreciated that handwriting may also be supplied to the system as an image, wherein a detailed time sequential behaviour, which is present in an on-line handwriting recognition system, is lost. The input signal is analysed using the signal analysing subsystem 354 and recognised by the unit matching subsystem 356, giving as the output 358 a recognition result, for instance in the form of text or control instructions.

According to the invention, the system 300 comprises means 335 for determining at least one context identifier. In a simple form, using conventional user interface means, such as a windowing system with dialogue boxes, a user of the system is requested to supply the context identifier. The system further comprises means 332 means for deriving at least one search criterion from the context identifier. Means 334 are used for selecting documents from a set of documents based on the search criterion. The selection may be performed in any suitable way, for instance by successively opening each of the documents of the set and inspecting the contents of the document to determine whether the document meets the selection criterion. The selection may also be performed by checking descriptive attributes, such as keywords, of a document (if available) against the criterion. Depending on the type of selection process, a document may be selected if one match with the criterion is fulfilled. Alternatively, for instance if the contents of the document is fully scanned, a document is only selected if the level of matching meets a predetermined matching level. The matching level may be an absolute level, such as the criterion has to be matched a predetermined number of times, or a relative level, for instance related to the size of the document. Means 336 are used for composing the training corpus from the selected documents. The composition may simply involve combining all selected documents. In practice, it is preferred to deal with all documents separately, where after an analysis of the document the outcome, in the form of an update to the vocabulary and/or the language model, is maintained but the document itself is no longer of any use to the system. Preferably, the system 300 comes with a default vocabulary and/or language model which is updated using the selected documents.

It will be appreciated that adding a new word to a vocabulary may, in itself, not be sufficient to ensure that the word can be recognised. For a speech recognition system a transcription in acoustic references is additionally required. For many languages, a reasonably accurate transcription can be achieved automatically for most words. By comparing a new word to words already in the vocabulary and having a transcription, a suitable transcription can be created. For instance, with a reasonably high accuracy a phonetic transcription can be made for a word based on phonetic transcriptions of known words. Even if the transcription is of only moderate quality, the new word will be present in the vocabulary and, preferably, also in the language model. This allows recognition of the word (which otherwise would not be possible) and, with the assistance of the language model, the recognition of the word may be of an acceptable level in its context. Once the word has been recognised, the transcription can automatically be adapted to better match the actual utterance for which the word is recognised. Alternatively, the transcription can be improved with the assistance of the user of the speech recognition system in the form of an acoustical training.

In a simple embodiment according to the invention, the context identifier is formed by one or more keywords, which act as the search criterion.

In an alternative embodiment, as shown in FIG. 4, the context identifier indicates a sequence of words, such as a phrase or a text. For instance, the user may enter via a user interface a string or indicate a text document. The system 300 comprises means 400 for extracting at least one keyword from the indicated sequence of words. The keywords act as the search criterion. Automatic methods for extracting keywords from a document are known in itself.

The set of documents from which the documents are selected may be formed by a document file system, such as, for instance, used in computer systems. Using conventional documents, the selection can be performed by scanning the contents of the document. Advantageously the set of documents is formed by a document database, such as a document management system. In such a system, as an alternative to or in addition to scanning the contents of the documents, also attributes describing the contents of the documents can be used for the selection.

In an embodiment according to the invention, as shown in FIG. 5, the set of documents is formed by documents in a distributed computer system 500. The distributed system 500 may range from a group of local computers within one building or site of a company, connected via a local area network, to a world-wide network of computers of different companies, connected via a wide area network, such as Internet. The distributed system 500 comprises several document stores; shown are 510, 520 and 530. In Internet term, the stores are referred to as servers. Also shown is one system 300 according to the invention. It will be appreciated that the distributed computer system 500 may be able to accommodate very many systems like 300.

In a further embodiment according to the invention, the distributed computer system 500 also comprises at least one network search engine 540. The system 300 comprises communication means 550 for supplying the search criterion to the network search engine 540. The network search engine 540 searches the document stores connected to the network 505 for documents meeting the search criterion. Such search engines are well known, particularly for Internet. Typically, the network search engine 540 regularly scans the distributed system 500 to determine which documents are available and to extract attributes, such as keywords, from the documents. The outcome of the scan is stored in a database of the search engine 540. The search is then performed on the database. The communication means 550 is also used for receiving the result of the search back from the search engine 540. Based on the indicated documents, the composition means 336 composes the training corpus. This will usually include using the communication means 550 to acquire the document from the document store indicated by the search engine 540. Alternatively, the search engine 540 may already have supplied the document to the system 300 as a result of the search.

In an alternative embodiment, the system 300 uses a network search agent to search through the stores 510, 520 and 530 of the network 505. To this end, the system 300 provides the search criterion to the search agent. The search agent autonomously searches stores in the network. Whenever a document fulfilling the search criterion is located the agent may deliver this to the system 300, for instance via regular e-mail. Various forms of search agents are known, particularly for Internet. For instance, the agent may be active only in the system 300, where it in turn (or in parallel) accesses stores in the distributed system, which respond to queries of the agent. Alternatively, the agent may move through the distributed system, e.g. by hopping from one server to another, where-the agent becomes active at the server it is ‘visiting’ at that moment.

In a further embodiment, the system 300 is operative to update the training corpus by at a later moment selecting at least one further document from the set of documents and combining the further document with at least one previously selected document to form the training corpus. Advantageously, a search engine or a search agent is used to select further documents based on the same search criterion as before. Preferably, the search criterion is updated based on documents recently recognised by the pattern recognition system, for instance by extracting keywords from recognised document(s). The updating may take place as a result of a direct instruction of a user. Alternatively, the updating may be autonomous and occur at regular moments.

Claims (14)

What is claimed is:
1. A method for establishing a vocabulary model and /or a statistical language model for subsequent use by a pattern recognition system, said method comprising:
receiving at least one context identifier;
deriving at least one search criterion from said at least one context identifier;
selecting a first set of at least one document based on said at least one search criterion;
composing a training corpus from said first set of at least one document;
selecting a second set of at least one document based on said at least one search criterion; and
modifying said training corpus to incorporate said second set of at least one document.
2. The method of claim 1, further comprising:
creating a vocabulary model from said training corpus.
3. The method of claim 1, further comprising:
creating a statistical language model from said training corpus.
4. The method of claim 1, further comprising:
modifying a vocabulary model in response to said modification of said training corpus.
5. The method of claim 1, further comprising:
modifying a statistical language model in response to said modification of said training corpus.
6. A system for establishing a language model, said system comprising:
a means for deriving at least one search criterion from said at least one context identifier;
a means for selecting a first set of at least one document based on said at least one search criterion;
a means for composing a training corpus from said first set of at least one document;
a means for selecting a second set of at least one document based on said at least one search criterion; and
a means for modifying said training corpus to incorporate said second set of at least one document.
7. The system of claim 6, further comprising:
a means for creating a vocabulary model from said training corpus.
8. The system of claim 6, further comprising:
a means for creating a statistical language model from said training corpus.
9. The system of claim 6, further comprising:
a means for modifying a vocabulary model in response to said modification of said training corpus.
10. The system of claim 6, further comprising:
a means for modifying a statistical language model in response to said modification of said training corpus.
11. In combination,
a computer system operable to establish a model, said computer system including
a means for receiving at least one context identifier,
a means for deriving at least one search criterion from said at least one context identifier,
a means for selecting a first set of at least one document based on said at least one search criterion,
a means for composing a training corpus from said first set of at least one document, and
a means for creating said model from said training corpus; and
a pattern recognition system operable to recognize a time-sequential input pattern based on said model.
12. The combination of claim 11, wherein said model is a vocabulary model.
13. The combination of claim 11, wherein said model is a statistical language model.
14. The combination of claim 11, wherein said computer system further includes
a means for selecting a second set of at least one document based on said at least one search criterion;
a means for modifying said training corpus to incorporate said second set of at least one document; and
a means for modifying said model in response to said modification of said training corpus.
US09167424 1997-10-08 1998-10-06 Vocabulary and/or language model training Expired - Fee Related US6430551B1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP97203124 1997-10-08
EP97203124 1997-10-08

Publications (1)

Publication Number Publication Date
US6430551B1 true US6430551B1 (en) 2002-08-06

Family

ID=8228802

Family Applications (1)

Application Number Title Priority Date Filing Date
US09167424 Expired - Fee Related US6430551B1 (en) 1997-10-08 1998-10-06 Vocabulary and/or language model training

Country Status (4)

Country Link
US (1) US6430551B1 (en)
EP (1) EP0979497A1 (en)
JP (1) JP2001507482A (en)
WO (1) WO1999018556A3 (en)

Cited By (72)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020013705A1 (en) * 2000-07-28 2002-01-31 International Business Machines Corporation Speech recognition by automated context creation
US20020194004A1 (en) * 2001-06-14 2002-12-19 Glinski Stephen C. Methods and systems for enabling speech-based internet searches
US20030009331A1 (en) * 2001-07-05 2003-01-09 Johan Schalkwyk Grammars for speech recognition
US20030182121A1 (en) * 2002-03-20 2003-09-25 Hwang Mei Yuh Generating a task-adapted acoustic model from one or more different corpora
US20030182120A1 (en) * 2002-03-20 2003-09-25 Mei Yuh Hwang Generating a task-adapted acoustic model from one or more supervised and/or unsupervised corpora
US20040034518A1 (en) * 2001-01-10 2004-02-19 Geog Rose Automatic dialog system with database language model
US20040088163A1 (en) * 2002-11-04 2004-05-06 Johan Schalkwyk Multi-lingual speech recognition with cross-language context modeling
US20040098263A1 (en) * 2002-11-15 2004-05-20 Kwangil Hwang Language model for use in speech recognition
US20040176953A1 (en) * 2002-10-24 2004-09-09 International Business Machines Corporation Method and apparatus for a interactive voice response system
US20040254795A1 (en) * 2001-07-23 2004-12-16 Atsushi Fujii Speech input search system
US20050004799A1 (en) * 2002-12-31 2005-01-06 Yevgenly Lyudovyk System and method for a spoken language interface to a large database of changing records
US20050102142A1 (en) * 2001-02-13 2005-05-12 Frederic Soufflet Method, module, device and server for voice recognition
US20050171783A1 (en) * 1999-07-17 2005-08-04 Suominen Edwin A. Message recognition using shared language model
US20050222848A1 (en) * 2001-10-15 2005-10-06 Napper Jonathan L Digital ink database searching using handwriting feature synthesis
US20050283475A1 (en) * 2004-06-22 2005-12-22 Beranek Michael J Method and system for keyword detection using voice-recognition
US20060002609A1 (en) * 2004-06-30 2006-01-05 Stefano Casadei Hierarchical optimization method and system for pattern recognition and edge detection
US20060053014A1 (en) * 2002-11-21 2006-03-09 Shinichi Yoshizawa Standard model creating device and standard model creating method
US20060212288A1 (en) * 2005-03-17 2006-09-21 Abhinav Sethy Topic specific language models built from large numbers of documents
US20070011117A1 (en) * 2005-06-27 2007-01-11 Microsoft Corporation Training with heterogeneous data
US7272558B1 (en) 2006-12-01 2007-09-18 Coveo Solutions Inc. Speech recognition training method for audio and video file indexing on a search engine
US20110153324A1 (en) * 2009-12-23 2011-06-23 Google Inc. Language Model Selection for Speech-to-Text Conversion
US20110191107A1 (en) * 2005-05-20 2011-08-04 Sony Computer Entertainment Inc. Structure for Grammar and Dictionary Representation in Voice Recognition and Method for Simplifying Link and Node-Generated Grammars
US20110208524A1 (en) * 2010-02-25 2011-08-25 Apple Inc. User profiling for voice input processing
US20120253799A1 (en) * 2011-03-28 2012-10-04 At&T Intellectual Property I, L.P. System and method for rapid customization of speech recognition models
USRE44248E1 (en) 1999-09-29 2013-05-28 Darrell A. Poirier System for transferring personalize matter from one computer to another
US8463786B2 (en) 2010-06-10 2013-06-11 Microsoft Corporation Extracting topically related keywords from related documents
WO2013172534A1 (en) * 2012-05-17 2013-11-21 포항공과대학교 산학협력단 System and method for managing dialogues
US8756064B2 (en) 2011-07-28 2014-06-17 Tata Consultancy Services Limited Method and system for creating frugal speech corpus using internet resources and conventional speech corpus
US8892446B2 (en) 2010-01-18 2014-11-18 Apple Inc. Service orchestration for intelligent automated assistant
US9081760B2 (en) 2011-03-08 2015-07-14 At&T Intellectual Property I, L.P. System and method for building diverse language models
US9262612B2 (en) 2011-03-21 2016-02-16 Apple Inc. Device access using voice authentication
US9300784B2 (en) 2013-06-13 2016-03-29 Apple Inc. System and method for emergency calls initiated by voice command
US9330720B2 (en) 2008-01-03 2016-05-03 Apple Inc. Methods and apparatus for altering audio output signals
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
US9368114B2 (en) 2013-03-14 2016-06-14 Apple Inc. Context-sensitive handling of interruptions
US9396726B2 (en) * 2014-06-26 2016-07-19 Nvoq Incorporated System and methods to create and determine when to use a minimal user specific language model
US9430463B2 (en) 2014-05-30 2016-08-30 Apple Inc. Exemplar-based natural language processing
US20160252972A1 (en) * 2015-02-28 2016-09-01 Samsung Electronics Co., Ltd. Synchronization of text data among a plurality of devices
US9483461B2 (en) 2012-03-06 2016-11-01 Apple Inc. Handling speech synthesis of content for multiple languages
US9495129B2 (en) 2012-06-29 2016-11-15 Apple Inc. Device, method, and user interface for voice-activated navigation and browsing of a document
US9502031B2 (en) 2014-05-27 2016-11-22 Apple Inc. Method for supporting dynamic grammars in WFST-based ASR
US9535906B2 (en) 2008-07-31 2017-01-03 Apple Inc. Mobile device having human language translation capability with positional feedback
US9576574B2 (en) 2012-09-10 2017-02-21 Apple Inc. Context-sensitive handling of interruptions by intelligent digital assistant
US9582608B2 (en) 2013-06-07 2017-02-28 Apple Inc. Unified ranking with entropy-weighted information for phrase-based semantic auto-completion
US9620105B2 (en) 2014-05-15 2017-04-11 Apple Inc. Analyzing audio input for efficient speech and music recognition
US9620104B2 (en) 2013-06-07 2017-04-11 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9626955B2 (en) 2008-04-05 2017-04-18 Apple Inc. Intelligent text-to-speech conversion
US9633004B2 (en) 2014-05-30 2017-04-25 Apple Inc. Better resolution when referencing to concepts
US9633674B2 (en) 2013-06-07 2017-04-25 Apple Inc. System and method for detecting errors in interactions with a voice-based digital assistant
US9646614B2 (en) 2000-03-16 2017-05-09 Apple Inc. Fast, language-independent method for user authentication by voice
US9646609B2 (en) 2014-09-30 2017-05-09 Apple Inc. Caching apparatus for serving phonetic pronunciations
US9668121B2 (en) 2014-09-30 2017-05-30 Apple Inc. Social reminders
US9697822B1 (en) 2013-03-15 2017-07-04 Apple Inc. System and method for updating an adaptive speech recognition model
US9697820B2 (en) 2015-09-24 2017-07-04 Apple Inc. Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks
US9711141B2 (en) 2014-12-09 2017-07-18 Apple Inc. Disambiguating heteronyms in speech synthesis
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
US9721566B2 (en) 2015-03-08 2017-08-01 Apple Inc. Competing devices responding to voice triggers
US9734193B2 (en) 2014-05-30 2017-08-15 Apple Inc. Determining domain salience ranking from ambiguous words in natural speech
US9760559B2 (en) 2014-05-30 2017-09-12 Apple Inc. Predictive text input
US9785630B2 (en) 2014-05-30 2017-10-10 Apple Inc. Text prediction using combined word N-gram and unigram language models
US9798393B2 (en) 2011-08-29 2017-10-24 Apple Inc. Text correction processing
US9818400B2 (en) 2014-09-11 2017-11-14 Apple Inc. Method and apparatus for discovering trending terms in speech requests
US9842105B2 (en) 2015-04-16 2017-12-12 Apple Inc. Parsimonious continuous-space phrase representations for natural language processing
US9842101B2 (en) 2014-05-30 2017-12-12 Apple Inc. Predictive conversion of language input
US9858925B2 (en) 2009-06-05 2018-01-02 Apple Inc. Using context information to facilitate processing of commands in a virtual assistant
US9865280B2 (en) 2015-03-06 2018-01-09 Apple Inc. Structured dictation using intelligent automated assistants
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US9886432B2 (en) 2014-09-30 2018-02-06 Apple Inc. Parsimonious handling of word inflection via categorical stem + suffix N-gram language models
US9899019B2 (en) 2015-03-18 2018-02-20 Apple Inc. Systems and methods for structured stem and suffix language models
WO2018039434A1 (en) * 2016-08-24 2018-03-01 Semantic Machines, Inc. Using paraphrase in accepting utterances in an automated assistant
US9922642B2 (en) 2013-03-15 2018-03-20 Apple Inc. Training an at least partial voice command system
US9934775B2 (en) 2016-09-15 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10014337A1 (en) * 2000-03-24 2001-09-27 Philips Corp Intellectual Pty Generating speech model involves successively reducing body of text on text data in user-specific second body of text, generating values of speech model using reduced first body of text
US8412521B2 (en) 2004-08-20 2013-04-02 Multimodal Technologies, Llc Discriminative training of document transcription system
US8335688B2 (en) 2004-08-20 2012-12-18 Multimodal Technologies, Llc Document transcription system training
JP4962416B2 (en) * 2008-06-03 2012-06-27 日本電気株式会社 Voice recognition system

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5278980A (en) * 1991-08-16 1994-01-11 Xerox Corporation Iterative technique for phrase query formation and an information retrieval system employing same
US5317507A (en) * 1990-11-07 1994-05-31 Gallant Stephen I Method for document retrieval and for word sense disambiguation using neural networks
US5742807A (en) * 1995-05-31 1998-04-21 Xerox Corporation Indexing system using one-way hash for document service
US5857169A (en) * 1995-08-28 1999-01-05 U.S. Philips Corporation Method and system for pattern recognition based on tree organized probability densities
US5920856A (en) * 1997-06-09 1999-07-06 Xerox Corporation System for selecting multimedia databases over networks
US5924105A (en) * 1997-01-27 1999-07-13 Michigan State University Method and product for determining salient features for use in information searching
US5933822A (en) * 1997-07-22 1999-08-03 Microsoft Corporation Apparatus and methods for an information retrieval system that employs natural language processing of search results to improve overall precision
US5970490A (en) * 1996-11-05 1999-10-19 Xerox Corporation Integration platform for heterogeneous databases
US6067541A (en) * 1997-09-17 2000-05-23 Microsoft Corporation Monitoring document changes in a file system of documents with the document change information stored in a persistent log
US6092045A (en) * 1997-09-19 2000-07-18 Nortel Networks Corporation Method and apparatus for speech recognition
US6363348B1 (en) * 1997-10-20 2002-03-26 U.S. Philips Corporation User model-improvement-data-driven selection and update of user-oriented recognition model of a given type for word recognition at network server

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4994983A (en) * 1989-05-02 1991-02-19 Itt Corporation Automatic speech recognition system using seed templates
EP0438662A3 (en) * 1990-01-23 1994-01-26 Ibm
US5390278A (en) * 1991-10-08 1995-02-14 Bell Canada Phoneme based speech recognition
US5502774A (en) * 1992-06-09 1996-03-26 International Business Machines Corporation Automatic recognition of a consistent message using multiple complimentary sources of information

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5317507A (en) * 1990-11-07 1994-05-31 Gallant Stephen I Method for document retrieval and for word sense disambiguation using neural networks
US5278980A (en) * 1991-08-16 1994-01-11 Xerox Corporation Iterative technique for phrase query formation and an information retrieval system employing same
US5742807A (en) * 1995-05-31 1998-04-21 Xerox Corporation Indexing system using one-way hash for document service
US5857169A (en) * 1995-08-28 1999-01-05 U.S. Philips Corporation Method and system for pattern recognition based on tree organized probability densities
US5970490A (en) * 1996-11-05 1999-10-19 Xerox Corporation Integration platform for heterogeneous databases
US5924105A (en) * 1997-01-27 1999-07-13 Michigan State University Method and product for determining salient features for use in information searching
US5920856A (en) * 1997-06-09 1999-07-06 Xerox Corporation System for selecting multimedia databases over networks
US5933822A (en) * 1997-07-22 1999-08-03 Microsoft Corporation Apparatus and methods for an information retrieval system that employs natural language processing of search results to improve overall precision
US6067541A (en) * 1997-09-17 2000-05-23 Microsoft Corporation Monitoring document changes in a file system of documents with the document change information stored in a persistent log
US6092045A (en) * 1997-09-19 2000-07-18 Nortel Networks Corporation Method and apparatus for speech recognition
US6363348B1 (en) * 1997-10-20 2002-03-26 U.S. Philips Corporation User model-improvement-data-driven selection and update of user-oriented recognition model of a given type for word recognition at network server

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
L. Raniner, B. H. Juang, "Fundamentals of Speech Recognition", Chapter 8, Large Vocabulary Continuous Speech Recognition, pps. 434-454, Prentice Hall, 1993.

Cited By (113)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8204737B2 (en) * 1999-07-17 2012-06-19 Optical Research Partners Llc Message recognition using shared language model
US20050171783A1 (en) * 1999-07-17 2005-08-04 Suominen Edwin A. Message recognition using shared language model
USRE44248E1 (en) 1999-09-29 2013-05-28 Darrell A. Poirier System for transferring personalize matter from one computer to another
US9646614B2 (en) 2000-03-16 2017-05-09 Apple Inc. Fast, language-independent method for user authentication by voice
US20020013705A1 (en) * 2000-07-28 2002-01-31 International Business Machines Corporation Speech recognition by automated context creation
US7243069B2 (en) * 2000-07-28 2007-07-10 International Business Machines Corporation Speech recognition by automated context creation
US7424428B2 (en) * 2001-01-10 2008-09-09 Koninklijke Philips Electronics N.V. Automatic dialog system with database language model
US20040034518A1 (en) * 2001-01-10 2004-02-19 Geog Rose Automatic dialog system with database language model
US20050102142A1 (en) * 2001-02-13 2005-05-12 Frederic Soufflet Method, module, device and server for voice recognition
US7983911B2 (en) * 2001-02-13 2011-07-19 Thomson Licensing Method, module, device and server for voice recognition
US20020194004A1 (en) * 2001-06-14 2002-12-19 Glinski Stephen C. Methods and systems for enabling speech-based internet searches
US7496515B2 (en) 2001-06-14 2009-02-24 Avaya, Inc. Methods and systems for enabling speech-based internet searches using phonemes
US6934675B2 (en) * 2001-06-14 2005-08-23 Stephen C. Glinski Methods and systems for enabling speech-based internet searches
US20050261906A1 (en) * 2001-06-14 2005-11-24 Glinski Stephen C Methods and systems for enabling speech-based internet searches
US20030009331A1 (en) * 2001-07-05 2003-01-09 Johan Schalkwyk Grammars for speech recognition
US20040254795A1 (en) * 2001-07-23 2004-12-16 Atsushi Fujii Speech input search system
US20050222848A1 (en) * 2001-10-15 2005-10-06 Napper Jonathan L Digital ink database searching using handwriting feature synthesis
US8219908B2 (en) * 2001-10-15 2012-07-10 Silverbrook Research Pty Ltd Digital ink database searching using handwriting feature synthesis
US20030182120A1 (en) * 2002-03-20 2003-09-25 Mei Yuh Hwang Generating a task-adapted acoustic model from one or more supervised and/or unsupervised corpora
US7031918B2 (en) 2002-03-20 2006-04-18 Microsoft Corporation Generating a task-adapted acoustic model from one or more supervised and/or unsupervised corpora
US20060036444A1 (en) * 2002-03-20 2006-02-16 Microsoft Corporation Generating a task-adapted acoustic model from one or more different corpora
US7006972B2 (en) * 2002-03-20 2006-02-28 Microsoft Corporation Generating a task-adapted acoustic model from one or more different corpora
US20030182121A1 (en) * 2002-03-20 2003-09-25 Hwang Mei Yuh Generating a task-adapted acoustic model from one or more different corpora
US7263487B2 (en) 2002-03-20 2007-08-28 Microsoft Corporation Generating a task-adapted acoustic model from one or more different corpora
US7318029B2 (en) * 2002-10-24 2008-01-08 International Business Machines Corporation Method and apparatus for a interactive voice response system
US20040176953A1 (en) * 2002-10-24 2004-09-09 International Business Machines Corporation Method and apparatus for a interactive voice response system
US20040088163A1 (en) * 2002-11-04 2004-05-06 Johan Schalkwyk Multi-lingual speech recognition with cross-language context modeling
US7149688B2 (en) 2002-11-04 2006-12-12 Speechworks International, Inc. Multi-lingual speech recognition with cross-language context modeling
US7584102B2 (en) * 2002-11-15 2009-09-01 Scansoft, Inc. Language model for use in speech recognition
EP1429313A3 (en) * 2002-11-15 2005-03-30 Scansoft, Inc. Language model for use in speech recognition
EP1429313A2 (en) * 2002-11-15 2004-06-16 Scansoft, Inc. Language model for use in speech recognition
US20040098263A1 (en) * 2002-11-15 2004-05-20 Kwangil Hwang Language model for use in speech recognition
US20060053014A1 (en) * 2002-11-21 2006-03-09 Shinichi Yoshizawa Standard model creating device and standard model creating method
US20090271201A1 (en) * 2002-11-21 2009-10-29 Shinichi Yoshizawa Standard-model generation for speech recognition using a reference model
US7603276B2 (en) * 2002-11-21 2009-10-13 Panasonic Corporation Standard-model generation for speech recognition using a reference model
US20050004799A1 (en) * 2002-12-31 2005-01-06 Yevgenly Lyudovyk System and method for a spoken language interface to a large database of changing records
US20050283475A1 (en) * 2004-06-22 2005-12-22 Beranek Michael J Method and system for keyword detection using voice-recognition
US7672845B2 (en) 2004-06-22 2010-03-02 International Business Machines Corporation Method and system for keyword detection using voice-recognition
US7738705B2 (en) * 2004-06-30 2010-06-15 Stefano Casadei Hierarchical method and system for pattern recognition and edge detection
US20060002609A1 (en) * 2004-06-30 2006-01-05 Stefano Casadei Hierarchical optimization method and system for pattern recognition and edge detection
US7739286B2 (en) * 2005-03-17 2010-06-15 University Of Southern California Topic specific language models built from large numbers of documents
US20060212288A1 (en) * 2005-03-17 2006-09-21 Abhinav Sethy Topic specific language models built from large numbers of documents
US20110191107A1 (en) * 2005-05-20 2011-08-04 Sony Computer Entertainment Inc. Structure for Grammar and Dictionary Representation in Voice Recognition and Method for Simplifying Link and Node-Generated Grammars
US8190433B2 (en) * 2005-05-20 2012-05-29 Sony Computer Entertainment Inc. Structure for grammar and dictionary representation in voice recognition and method for simplifying link and node-generated grammars
US20070011117A1 (en) * 2005-06-27 2007-01-11 Microsoft Corporation Training with heterogeneous data
US7593908B2 (en) 2005-06-27 2009-09-22 Microsoft Corporation Training with heterogeneous data
US9117447B2 (en) 2006-09-08 2015-08-25 Apple Inc. Using event alert text as input to an automated assistant
US8930191B2 (en) 2006-09-08 2015-01-06 Apple Inc. Paraphrasing of user requests and results by automated digital assistant
US8942986B2 (en) 2006-09-08 2015-01-27 Apple Inc. Determining user intent based on ontologies of domains
US7272558B1 (en) 2006-12-01 2007-09-18 Coveo Solutions Inc. Speech recognition training method for audio and video file indexing on a search engine
US9330720B2 (en) 2008-01-03 2016-05-03 Apple Inc. Methods and apparatus for altering audio output signals
US9865248B2 (en) 2008-04-05 2018-01-09 Apple Inc. Intelligent text-to-speech conversion
US9626955B2 (en) 2008-04-05 2017-04-18 Apple Inc. Intelligent text-to-speech conversion
US9535906B2 (en) 2008-07-31 2017-01-03 Apple Inc. Mobile device having human language translation capability with positional feedback
US9858925B2 (en) 2009-06-05 2018-01-02 Apple Inc. Using context information to facilitate processing of commands in a virtual assistant
US9495127B2 (en) * 2009-12-23 2016-11-15 Google Inc. Language model selection for speech-to-text conversion
US9251791B2 (en) 2009-12-23 2016-02-02 Google Inc. Multi-modal input on an electronic device
US20110153324A1 (en) * 2009-12-23 2011-06-23 Google Inc. Language Model Selection for Speech-to-Text Conversion
US9548050B2 (en) 2010-01-18 2017-01-17 Apple Inc. Intelligent automated assistant
US8892446B2 (en) 2010-01-18 2014-11-18 Apple Inc. Service orchestration for intelligent automated assistant
US8903716B2 (en) 2010-01-18 2014-12-02 Apple Inc. Personalized vocabulary for digital assistant
US9318108B2 (en) 2010-01-18 2016-04-19 Apple Inc. Intelligent automated assistant
US9190062B2 (en) 2010-02-25 2015-11-17 Apple Inc. User profiling for voice input processing
US9633660B2 (en) 2010-02-25 2017-04-25 Apple Inc. User profiling for voice input processing
US20110208524A1 (en) * 2010-02-25 2011-08-25 Apple Inc. User profiling for voice input processing
US8682667B2 (en) * 2010-02-25 2014-03-25 Apple Inc. User profiling for selecting user specific voice input processing information
US8463786B2 (en) 2010-06-10 2013-06-11 Microsoft Corporation Extracting topically related keywords from related documents
US9081760B2 (en) 2011-03-08 2015-07-14 At&T Intellectual Property I, L.P. System and method for building diverse language models
US9396183B2 (en) 2011-03-08 2016-07-19 At&T Intellectual Property I, L.P. System and method for building diverse language models
US9727557B2 (en) 2011-03-08 2017-08-08 Nuance Communications, Inc. System and method for building diverse language models
US9262612B2 (en) 2011-03-21 2016-02-16 Apple Inc. Device access using voice authentication
US9679561B2 (en) * 2011-03-28 2017-06-13 Nuance Communications, Inc. System and method for rapid customization of speech recognition models
US20120253799A1 (en) * 2011-03-28 2012-10-04 At&T Intellectual Property I, L.P. System and method for rapid customization of speech recognition models
US8756064B2 (en) 2011-07-28 2014-06-17 Tata Consultancy Services Limited Method and system for creating frugal speech corpus using internet resources and conventional speech corpus
US9798393B2 (en) 2011-08-29 2017-10-24 Apple Inc. Text correction processing
US9483461B2 (en) 2012-03-06 2016-11-01 Apple Inc. Handling speech synthesis of content for multiple languages
US9514742B2 (en) 2012-05-17 2016-12-06 Postech Academy-Industry Foundation System and method for managing conversation
WO2013172534A1 (en) * 2012-05-17 2013-11-21 포항공과대학교 산학협력단 System and method for managing dialogues
US9495129B2 (en) 2012-06-29 2016-11-15 Apple Inc. Device, method, and user interface for voice-activated navigation and browsing of a document
US9576574B2 (en) 2012-09-10 2017-02-21 Apple Inc. Context-sensitive handling of interruptions by intelligent digital assistant
US9368114B2 (en) 2013-03-14 2016-06-14 Apple Inc. Context-sensitive handling of interruptions
US9697822B1 (en) 2013-03-15 2017-07-04 Apple Inc. System and method for updating an adaptive speech recognition model
US9922642B2 (en) 2013-03-15 2018-03-20 Apple Inc. Training an at least partial voice command system
US9582608B2 (en) 2013-06-07 2017-02-28 Apple Inc. Unified ranking with entropy-weighted information for phrase-based semantic auto-completion
US9633674B2 (en) 2013-06-07 2017-04-25 Apple Inc. System and method for detecting errors in interactions with a voice-based digital assistant
US9620104B2 (en) 2013-06-07 2017-04-11 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9300784B2 (en) 2013-06-13 2016-03-29 Apple Inc. System and method for emergency calls initiated by voice command
US9620105B2 (en) 2014-05-15 2017-04-11 Apple Inc. Analyzing audio input for efficient speech and music recognition
US9502031B2 (en) 2014-05-27 2016-11-22 Apple Inc. Method for supporting dynamic grammars in WFST-based ASR
US9760559B2 (en) 2014-05-30 2017-09-12 Apple Inc. Predictive text input
US9785630B2 (en) 2014-05-30 2017-10-10 Apple Inc. Text prediction using combined word N-gram and unigram language models
US9633004B2 (en) 2014-05-30 2017-04-25 Apple Inc. Better resolution when referencing to concepts
US9430463B2 (en) 2014-05-30 2016-08-30 Apple Inc. Exemplar-based natural language processing
US9734193B2 (en) 2014-05-30 2017-08-15 Apple Inc. Determining domain salience ranking from ambiguous words in natural speech
US9715875B2 (en) 2014-05-30 2017-07-25 Apple Inc. Reducing the need for manual start/end-pointing and trigger phrases
US9842101B2 (en) 2014-05-30 2017-12-12 Apple Inc. Predictive conversion of language input
US9396726B2 (en) * 2014-06-26 2016-07-19 Nvoq Incorporated System and methods to create and determine when to use a minimal user specific language model
US9668024B2 (en) 2014-06-30 2017-05-30 Apple Inc. Intelligent automated assistant for TV user interactions
US9338493B2 (en) 2014-06-30 2016-05-10 Apple Inc. Intelligent automated assistant for TV user interactions
US9818400B2 (en) 2014-09-11 2017-11-14 Apple Inc. Method and apparatus for discovering trending terms in speech requests
US9886432B2 (en) 2014-09-30 2018-02-06 Apple Inc. Parsimonious handling of word inflection via categorical stem + suffix N-gram language models
US9646609B2 (en) 2014-09-30 2017-05-09 Apple Inc. Caching apparatus for serving phonetic pronunciations
US9668121B2 (en) 2014-09-30 2017-05-30 Apple Inc. Social reminders
US9711141B2 (en) 2014-12-09 2017-07-18 Apple Inc. Disambiguating heteronyms in speech synthesis
US20160252972A1 (en) * 2015-02-28 2016-09-01 Samsung Electronics Co., Ltd. Synchronization of text data among a plurality of devices
US9865280B2 (en) 2015-03-06 2018-01-09 Apple Inc. Structured dictation using intelligent automated assistants
US9721566B2 (en) 2015-03-08 2017-08-01 Apple Inc. Competing devices responding to voice triggers
US9886953B2 (en) 2015-03-08 2018-02-06 Apple Inc. Virtual assistant activation
US9899019B2 (en) 2015-03-18 2018-02-20 Apple Inc. Systems and methods for structured stem and suffix language models
US9842105B2 (en) 2015-04-16 2017-12-12 Apple Inc. Parsimonious continuous-space phrase representations for natural language processing
US9697820B2 (en) 2015-09-24 2017-07-04 Apple Inc. Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks
WO2018039434A1 (en) * 2016-08-24 2018-03-01 Semantic Machines, Inc. Using paraphrase in accepting utterances in an automated assistant
US9934775B2 (en) 2016-09-15 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters

Also Published As

Publication number Publication date Type
WO1999018556A3 (en) 1999-06-24 application
WO1999018556A2 (en) 1999-04-15 application
EP0979497A1 (en) 2000-02-16 application
JP2001507482A (en) 2001-06-05 application

Similar Documents

Publication Publication Date Title
Young et al. The HTK hidden Markov model toolkit: Design and philosophy
US6587822B2 (en) Web-based platform for interactive voice response (IVR)
US7315818B2 (en) Error correction in speech recognition
US7191118B2 (en) Method for dynamic context scope selection in hybrid N-gram+LSA language modeling
US6212498B1 (en) Enrollment in speech recognition
US5699456A (en) Large vocabulary connected speech recognition system and method of language representation using evolutional grammar to represent context free grammars
US6999932B1 (en) Language independent voice-based search system
US6345252B1 (en) Methods and apparatus for retrieving audio information using content and speaker information
US6738745B1 (en) Methods and apparatus for identifying a non-target language in a speech recognition system
US5870706A (en) Method and apparatus for an improved language recognition system
US5878386A (en) Natural language parser with dictionary-based part-of-speech probabilities
US6208964B1 (en) Method and apparatus for providing unsupervised adaptation of transcriptions
US8374871B2 (en) Methods for creating a phrase thesaurus
US6243680B1 (en) Method and apparatus for obtaining a transcription of phrases through text and spoken utterances
US20040254795A1 (en) Speech input search system
US7197460B1 (en) System for handling frequently asked questions in a natural language dialog service
US6952665B1 (en) Translating apparatus and method, and recording medium used therewith
US5680511A (en) Systems and methods for word recognition
US5231670A (en) Voice controlled system and method for generating text from a voice controlled input
US20040138881A1 (en) Automatic insertion of non-verbalized punctuation
US7016849B2 (en) Method and apparatus for providing speech-driven routing between spoken language applications
US7552053B2 (en) Techniques for aiding speech-to-speech translation
He et al. A data-driven spoken language understanding system
US6501833B2 (en) Method and apparatus for dynamic adaptation of a large vocabulary speech recognition system and for use of constraints from a database in a large vocabulary speech recognition system
US20040148154A1 (en) System for using statistical classifiers for spoken language understanding

Legal Events

Date Code Title Description
AS Assignment

Owner name: U.S. PHILIPS CORPORATION, NEW YORK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:THELEN, ERIC;BESLING, STEFAN;DEJARNETT, STEVE;REEL/FRAME:009642/0992;SIGNING DATES FROM 19981021 TO 19981110

AS Assignment

Owner name: KONINKLIJKE PHILIPS ELECTRONICS N.V., NETHERLANDS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:U.S. PHILIPS CORPORATION;REEL/FRAME:013014/0290

Effective date: 20020607

FPAY Fee payment

Year of fee payment: 4

REMI Maintenance fee reminder mailed
LAPS Lapse for failure to pay maintenance fees
FP Expired due to failure to pay maintenance fee

Effective date: 20100806